This paper presents an evaluation of how data augmentation and inter-class transformations can be used to synthesize training data in low-data scenarios for single-image weather classification. In such scenarios, augmentations is a critical component, but there is a limit to how much improvements can be gained using classical augmentation strategies. Generative adversarial networks (GAN) have been demonstrated to generate impressive results, and have also been successful as a tool for data augmentation, but mostly for images of limited diversity, such as in medical applications. We investigate the possibilities in using generative augmentations for balancing a small weather classification dataset, where one class has a reduced number of images. We compare intra-class augmentations by means of classical transformations as well as noise-to-image GANs, to interclass augmentations where images from another class are transformed to the underrepresented class. The results show that it is possible to take advantage of GANs for inter-class augmentations to balance a small dataset for weather classification. This opens up for future work on GAN-based augmentations in scenarios where data is both diverse and scarce.
Apostolia Tsirikoglou, Marcus Gladh, Daniel Sahlin, Gabriel Eilertsen, Jonas Unger, "Generative inter-class transformations for imbalanced data weather classification" in Proc. IS&T London Imaging Meeting 2021: Imaging for Deep Learning, 2021, pp 16 - 20, https://doi.org/10.2352/issn.2694-118X.2021.LIM-16